TAU2
Measured Jul 10, 2026Source
Score
0.94
Models11 0 
DeepSeek V4 Pro (Reasoning, High Effort)
DeepSeekDeepSeekChina
A high-effort reasoning model from the DeepSeek V4 series, optimized for complex problem-solving and deep analytical tasks. It likely employs extended thinking or chain-of-thought processes to tackle challenging queries in coding, mathematics, and logic.
CodingReasoning
Input / 1M tokens
$0.435Output / 1M tokens
$0.87Output tokens/s
57.99First-token seconds
1.06sSupported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured Jul 10, 2026Source
Score
0.42
Lcr
Measured Jul 10, 2026Source
Score
0.65
Ifbench
Measured Jul 10, 2026Source
Score
0.71
Scicode
Measured Jul 10, 2026Source
Score
0.46
Hle
Measured Jul 10, 2026Source
Score
0.34
Gpqa
Measured Jul 10, 2026Source
Score
0.91
Artificial Analysis Intelligence Index
Measured Jul 10, 2026Source
Score
40.8
Tau Banking
Measured Jul 10, 2026Source
Score
0.26
Terminalbench V2 1
Measured Jul 10, 2026Source
Score
0.64
Artificial Analysis Coding Index
Measured Jul 10, 2026Source
Score
59.4
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server